authorship-strategy-skill

# authorship-strategy-skill

> A Claude Code skill (documentation-only, MIT, no tagged release yet) that loads the judgment framework of the [`authorship-strategy`](https://github.com/shimo4228/authorship-strategy) research line into an LLM-based coding agent: how a maker gets ideas used and keeps the source attached as they spread, including when readers meet them through LLMs. It evaluates a concrete plan against the framework applied to the user's current goals, checks the concerns before the plan is adopted, or explains the framework, and answers with the plan's value and concerns rather than a pass/fail table. Three inversions (scarcity → wide use, exclusivity → derivation and reuse, enclosure → open access and reuse) and four viewpoints (Authenticity, Attribution diffusion, Idea / scaffold, Tactics) are treated as material for judgment, not as a gate. Status: active, synced one way from the author's Claude Code harness.

## Core documentation

- [SKILL.md](skills/authorship-strategy/SKILL.md): the skill itself (in Japanese) — when it applies (evaluating a concrete plan, checking concerns before adoption, explaining the framework; not open brainstorming, next-idea generation or day-to-day coding), the framework as material rather than a gate, references read on demand, and how records follow the adopting project's own ledger
- [strategy-reference.md](skills/authorship-strategy/references/strategy-reference.md): the framework explained — the maker's purpose, the three inversions, the four viewpoints, audience and observation, making sources traceable
- [action-review.md](skills/authorship-strategy/references/action-review.md): conditions checked only when they apply to a concrete action — purpose and feasibility, sources and outputs, external actions (posting, registering, publishing), the record afterwards
- [provenance-layer-prompt.md](skills/authorship-strategy/provenance-layer-prompt.md): a task prompt used only when provenance edits to a repository's `graph.jsonld` are explicitly requested
- [README.md](README.md): human-facing narrative (when to use, install, how it works, the framework in brief)
- [inspiration.md](inspiration.md): where the framework came from
- [CHANGELOG.md](CHANGELOG.md): release notes (its Unreleased section still describes the earlier version of the skill)

## When the skill applies

The skill loads for a narrow trigger:

- Evaluating a concrete plan against the framework ("evaluate this plan from the authorship-strategy angle")
- Checking the concerns before adopting or carrying out a plan
- Explaining the existing framework

It does not load for open brainstorming, generating the next idea, or day-to-day coding, and working inside a research repository is not by itself a reason to apply it. When invoked by name to explore an idea, the purpose of the request comes first. In someone else's project, that author's goals and policy take precedence.

## Key concept

The framework records judgment from past practice, so fitting a plan into it is not counted as success. When a plan conflicts with the framework, the agent says which premise differs and what is gained and lost; revising the framework is one of the options. The three inversions are claims of the framework, not a demonstrated result that publishing always preserves the source; publication, reuse and attribution to the author are checked separately.

## Doctrine repository

- [authorship-strategy](https://github.com/shimo4228/authorship-strategy): the doctrine behind this skill — thesis, dated design decisions (ADRs) whose numbers the skill files cite, preliminary measurements, glossary, manifesto; concept DOI 10.5281/zenodo.20263316

## Related skills

This skill works on its own. The author keeps separate skills for neighbouring tasks:

- [release-doi](https://github.com/shimo4228/release-doi): release-time workflow for DOI-registered repos (verify, tag, deposit, propagate DOI)
- [citation-sync](https://github.com/shimo4228/citation-sync): keeping a research repo's cited literature in step across docs, `.zenodo.json` and `graph.jsonld`
- [llms-txt-writer](https://github.com/shimo4228/llms-txt-writer): AI-facing documentation prose
- [jsonld-knowledge-graph](https://github.com/shimo4228/jsonld-knowledge-graph): JSON-LD knowledge graph design
- [context-sync](https://github.com/shimo4228/context-sync): cross-document drift audits
- [claude-skill-writing-ecosystem](https://github.com/shimo4228/claude-skill-writing-ecosystem): human-facing writing orchestrator

## Optional

- [authorship-strategy-rules](https://github.com/shimo4228/authorship-strategy-rules): a frozen public record of the same framework as one always-loaded rules file, superseded by this skill
- [shimo4228](https://github.com/shimo4228/shimo4228): the author's hub — Authorship Strategy next to the author's other practice lines and their concept DOIs